Solving stochastic optimization problems under partial observability, where one needs to adaptively make decisions with uncertain outcomes, is a fundamental but notoriously diffic...
In traditional game theory, players are typically endowed with exogenously given knowledge of the structure of the game—either full omniscient knowledge or partial but fixed in...
Matt Lepinski, David Liben-Nowell, Seth Gilbert, A...
My research attempts to address on-line action selection in reinforcement learning from a Bayesian perspective. The idea is to develop more effective action selection techniques b...
Predictive state representations (PSRs) have recently been proposed as an alternative to partially observable Markov decision processes (POMDPs) for representing the state of a dy...
Matthew Rosencrantz, Geoffrey J. Gordon, Sebastian...
The CSISM project is designing and implementing an automated cyberdefense decision-making mechanism with expert-level ability. CSISM interprets alerts and observations and takes d...
D. Paul Benjamin, Partha Pratim Pal, Franklin Webb...